def normalize_path_maybe_ignore(path: Path, root: Path,
report: Report) -> Optional[str]:
"""Normalize `path`. May return `None` if `path` was ignored.
`report` is where "path ignored" output goes.
"""
try:
abspath = path if path.is_absolute() else Path.cwd() / path
normalized_path = abspath.resolve().relative_to(root).as_posix()
except OSError as e:
report.path_ignored(path, f"cannot be read because {e}")
return None
except ValueError:
if path.is_symlink():
report.path_ignored(
path, f"is a symbolic link that points outside {root}")
return None
raise
return normalized_path
def gen_python_files(
paths: Iterable[Path],
root: Path,
include: Pattern[str],
exclude: Pattern[str],
extend_exclude: Optional[Pattern[str]],
force_exclude: Optional[Pattern[str]],
report: Report,
gitignore: Optional[PathSpec],
*,
verbose: bool,
quiet: bool,
) -> Iterator[Path]:
"""Generate all files under `path` whose paths are not excluded by the
`exclude_regex`, `extend_exclude`, or `force_exclude` regexes,
but are included by the `include` regex.
Symbolic links pointing outside of the `root` directory are ignored.
`report` is where output about exclusions goes.
"""
assert root.is_absolute(
), f"INTERNAL ERROR: `root` must be absolute but is {root}"
for child in paths:
normalized_path = normalize_path_maybe_ignore(child, root, report)
if normalized_path is None:
continue
# First ignore files matching .gitignore, if passed
if gitignore is not None and gitignore.match_file(normalized_path):
report.path_ignored(child, "matches the .gitignore file content")
continue
# Then ignore with `--exclude` `--extend-exclude` and `--force-exclude` options.
normalized_path = "/" + normalized_path
if child.is_dir():
normalized_path += "/"
if path_is_excluded(normalized_path, exclude):
report.path_ignored(child,
"matches the --exclude regular expression")
continue
if path_is_excluded(normalized_path, extend_exclude):
report.path_ignored(
child, "matches the --extend-exclude regular expression")
continue
if path_is_excluded(normalized_path, force_exclude):
report.path_ignored(
child, "matches the --force-exclude regular expression")
continue
if child.is_dir():
# If gitignore is None, gitignore usage is disabled, while a Falsey
# gitignore is when the directory doesn't have a .gitignore file.
yield from gen_python_files(
child.iterdir(),
root,
include,
exclude,
extend_exclude,
force_exclude,
report,
gitignore +
get_gitignore(child) if gitignore is not None else None,
verbose=verbose,
quiet=quiet,
)
elif child.is_file():
if child.suffix == ".ipynb" and not jupyter_dependencies_are_installed(
verbose=verbose, quiet=quiet):
continue
include_match = include.search(
normalized_path) if include else True
if include_match:
yield child